spapr_iommu: Add root memory region

We are going to have multiple DMA windows at different offsets on
a PCI bus. For the sake of migration, we will have as many TCE table
objects pre-created as many windows supported.
So we need a way to map windows dynamically onto a PCI bus
when migration of a table is completed but at this stage a TCE table
object does not have access to a PHB to ask it to map a DMA window
backed by just migrated TCE table.

This adds a "root" memory region (UINT64_MAX long) to the TCE object.
This new region is mapped on a PCI bus with enabled overlapping as
there will be one root MR per TCE table, each of them mapped at 0.
The actual IOMMU memory region is a subregion of the root region and
a TCE table enables/disables this subregion and maps it at
the specific offset inside the root MR which is 1:1 mapping of
a PCI address space.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

2 files changed, 13 insertions, 6 deletions

diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c
index 28991bc370..a3cc5722f1 100644
--- a/hw/ppc/spapr_iommu.c
+++ b/hw/ppc/spapr_iommu.c
@@ -233,11 +233,16 @@ static MemoryRegionIOMMUOps spapr_iommu_ops = {
 static int spapr_tce_table_realize(DeviceState *dev)
 {
     sPAPRTCETable *tcet = SPAPR_TCE_TABLE(dev);
+    Object *tcetobj = OBJECT(tcet);
+    char tmp[32];
 
     tcet->fd = -1;
     tcet->need_vfio = false;
-    memory_region_init_iommu(&tcet->iommu, OBJECT(dev), &spapr_iommu_ops,
-                             "iommu-spapr", 0);
+    snprintf(tmp, sizeof(tmp), "tce-root-%x", tcet->liobn);
+    memory_region_init(&tcet->root, tcetobj, tmp, UINT64_MAX);
+
+    snprintf(tmp, sizeof(tmp), "tce-iommu-%x", tcet->liobn);
+    memory_region_init_iommu(&tcet->iommu, tcetobj, &spapr_iommu_ops, tmp, 0);
 
     QLIST_INSERT_HEAD(&spapr_tce_tables, tcet, list);
 
@@ -321,6 +326,7 @@ void spapr_tce_table_enable(sPAPRTCETable *tcet,
 
     memory_region_set_size(&tcet->iommu,
                            (uint64_t)tcet->nb_table << tcet->page_shift);
+    memory_region_add_subregion(&tcet->root, tcet->bus_offset, &tcet->iommu);
 }
 
 void spapr_tce_table_disable(sPAPRTCETable *tcet)
@@ -329,6 +335,7 @@ void spapr_tce_table_disable(sPAPRTCETable *tcet)
         return;
     }
 
+    memory_region_del_subregion(&tcet->root, &tcet->iommu);
     memory_region_set_size(&tcet->iommu, 0);
 
     spapr_tce_free_table(tcet->table, tcet->fd, tcet->nb_table);
@@ -350,7 +357,7 @@ static void spapr_tce_table_unrealize(DeviceState *dev, Error **errp)
 
 MemoryRegion *spapr_tce_get_iommu(sPAPRTCETable *tcet)
 {
-    return &tcet->iommu;
+    return &tcet->root;
 }
 
 static void spapr_tce_reset(DeviceState *dev)
diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c
index 7688ae073a..a529effe0d 100644
--- a/hw/ppc/spapr_pci.c
+++ b/hw/ppc/spapr_pci.c
@@ -1470,13 +1470,13 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp)
         return;
     }
 
+    memory_region_add_subregion_overlap(&sphb->iommu_root, 0,
+                                        spapr_tce_get_iommu(tcet), 0);
+
     /* Register default 32bit DMA window */
     spapr_tce_table_enable(tcet, SPAPR_TCE_PAGE_SHIFT, sphb->dma_win_addr,
                            nb_table);
 
-    memory_region_add_subregion(&sphb->iommu_root, tcet->bus_offset,
-                                spapr_tce_get_iommu(tcet));
-
     sphb->msi = g_hash_table_new_full(g_int_hash, g_int_equal, g_free, g_free);
 }